Graphics Architecture

Thursday, 9 August
8:30 - 10:15 am
Room 6CF
Session Chair/Discussant: Greg Humphreys, University of Virginia

Fast Triangle Reordering for Vertex Locality and Reduced Overdraw

Extremely efficient, novel algorithms that reorder triangles for post-transform vertex cache efficiency view-independent overdraw reduction, suitable for use in run-time.

Pedro Sander
Hong Kong University of Science and Technology

Diego Nehab
Princeton University

Joshua Barczak
Advanced Micro Devices, Inc.

A Hardware Architecture for Surface Splatting

This architecture for hardware-accelerated rendering of point primitives implements a refined version of EWA splatting and allows for integration into conventional graphics pipelines to complement triangle-based rendering.

Tim Weyrich
ETH Zürich and Princeton University

Simon Heinzle
ETH Zürich

Timo Aila
Helsinki University of Technology and NVIDIA Research

Daniel B. Fasnacht
Stephan Oetiker
Mario Botsch
Daniel Fasnacht
Cyril Flaig
Simon Mall
Kaspar Rohrer
Norbert Felber
Hubert Kaeslin
Markus Gross
ETH Zürich

Direct Manipulation of Subdivision Surfaces on GPUs

An algorithm for real-time deformation of subdivision surfaces, including displaced subdivision surfaces and subdivision surfaces with geometric textures.

Kun Zhou
Xin Huang
Weiwei Xu
Baining Guo
Heung-Yeung Shum
Microsoft Research Asia

PCU: The Programmable Culling Unit

The programmable culling unit is as flexible as the fragment program unit and capable of rapidly culling entire blocks of fragments.

Jon Hasselgren
Tomas Akenine-Möller
Lund University